nodejs encoding using request

Question

I am trying to get the correct encoding with request.

request.get({
    "uri":'http://www.bold.dk/tv/',
    "encoding": "text/html;charset='charset=utf-8'"
  },
  function(err, resp, body){    
    console.log(body);
  }
);

No matter what I do the encoding of the danish chars are not right.

Any thoughts?

Answer 1

You can use iconv (lite) to convert this. You also need to tell request not to actively set the encoding to the default of UTF-8 by setting the encoding property to null. Therefore you should do:

var iconv = require('iconv-lite');
request.get({
    uri:'http://www.bold.dk/tv/',
    encoding: null
  },
  function(err, resp, body){    
    var bodyWithCorrectEncoding = iconv.decode(body, 'iso-8859-1');
    console.log(bodyWithCorrectEncoding);
  }
);

Answer 2

Maybe your trouble is in 'Accept-Encoding' header. Let's say you have Headers like 'Accept-Encoding': 'gzip,deflate'

If it's so, you have 2 ways to fixing this:

1. Remove this Header

2. Use the following code to unzip the data:

   const req = request(options, res => {
       let buffers = []
       let bufferLength = 0
       let strings = []
   
       const getData = chunk => {
           if (!Buffer.isBuffer(chunk)) {
               strings.push(chunk)
           } else if (chunk.length) {
               bufferLength += chunk.length
               buffers.push(chunk)
           }
       }
   
       const endData = () => {
           let response = {code: 200, body: ''}
           if (bufferLength) {
               response.body = Buffer.concat(buffers, bufferLength)
               if (options.encoding !== null) {
                   response.body = response.body.toString(options.encoding)
               }
               buffers = []
               bufferLength = 0
           } else if (strings.length) {
               if (options.encoding === 'utf8' && strings[0].length > 0 && strings[0][0] === '\uFEFF') {
                   strings[0] = strings[0].substring(1)
               }
               response.body = strings.join('')
           }
           console.log('response', response)
       };
   
       switch (res.headers['content-encoding']) {
           // or, just use zlib.createUnzip() to handle both cases
           case 'gzip':
               res.pipe(zlib.createGunzip())
                   .on('data', getData)
                   .on('end', endData)
               break;
           case 'deflate':
               res.pipe(zlib.createInflate())
                   .on('data', getData)
                   .on('end', endData)
               break;
           default:
               res.pipe(zlib.createInflate())
                   .on('data', getData)
                   .on('end', endData)
               break;
       }
   });